Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already carry readOnlyHint/destructiveHint/openWorldHint; the description adds genuine context beyond them—return shape, shared backing store, tenant scoping, and that edits live outside MCP. That extra context earns above the annotation-adjusted baseline.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded purpose sentence, then return shape and caveats, then REQUIRED and EXAMPLE. Slightly dense with tenant/backing-store asides but each sentence carries usable signal.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema, yet the description supplies the return shape; required param and example are present. The undocumented connection_context parameter is the main remaining gap for an otherwise complete read tool definition.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% (only required product_id typed, connection_context undocumented), so the description must compensate. It documents product_id origin (product_ref from products_list), legacy id acceptance, and a call example; connection_context remains undocumented, keeping it from a 5.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource: returns AppsFlyer MMP event candidates for one product, and explicitly labels it metadata discovery rather than mutation. Distinguishes from product mutations, though not sharply from sibling products_list / products_get_top_campaigns beyond the 'event candidates' framing.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implies discovery usage and clarifies it is read-only, but does not say when to choose this over products_list or mmp_insights_get_product_event_today, nor when not to use it. Usage is inferable but not explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.